Hi! I’m Nenden Amelia, a detail-oriented freelancer with solid experience in AI testing, prompt engineering, and large language model (LLM) evaluation. I specialize in crafting high-quality prompts, refining rubrics, and assessing AI outputs across English and Bahasa Indonesia for both fluency and cultural accuracy.
Over the past few years, I’ve collaborated with leading global companies such as Microsoft, Meta, Uber (Centific), RWS Group, and more. My role involved annotating AI responses, conducting pairwise comparisons, and providing actionable feedback to enhance model performance and safety. I’ve worked on real-world applications in Microsoft 365 Copilot, Meta's multilingual LLM evaluation, and Uber’s AI testing pipeline.
My skills include:
Prompt Engineering & Rubric Design
AI Output Evaluation (Accuracy, Alignment, Naturalness)
Multilingual Annotation (EN & ID)
Data Labeling for NLP
Tools: SPSS, AnyLogic, Vensim, Excel
With a strong academic background (Logistics Systems, GPA 3.94) and a passion for AI ethics and quality, I bring a unique blend of technical precision and linguistic insight. Whether you're developing a new LLM, testing prompts, or need reliable annotation work, I’m here to help you deliver accurate, safe, and user-aligned AI solutions.
Loading ...
